Excalidraw Canvas
Provides a local-first Excalidraw canvas with MCP tools to read and modify boards, add images, manage anchored image comment threads, export data, and open an interactive Excalidraw UI, with revision checks to preserve concurrent edits.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Excalidraw CanvasCreate a payment flow board with user, order service, payment gateway, and callback."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Excalidraw Canvas for Codex
在 Codex 里使用真正的 Excalidraw 画布:通过 MCP 创建与修改画板,把评论钉在图片上的具体位置,并从支持 MCP Apps 的宿主侧栏打开交互界面。
English: A local-first Excalidraw plugin with MCP tools, an MCP App, and reusable skills. Review images with anchored comment threads, edit boards from Codex, and preserve concurrent changes with revision checks.

功能
Excalidraw 画布:自由绘图、图形、文本、图片与画板切换。
图片评论:在图片上定位评论,回复、解决和查看讨论;锚点随图片移动、缩放、旋转和翻转。
Codex MCP 控制:读取画板、增加或修改元素、插入图片、管理评论、导出数据。
MCP App:
open_canvas声明全局侧栏与对话侧栏入口,提供同一套交互界面。宿主版本与插件安装状态决定入口是否实际显示。本地持久化:画板与图片存储在本机;UI 和 MCP 调用共享数据。场景写入使用 revision 比较,避免无提示覆盖其他窗口的更改。
完整插件组织:portable manifest + stdio MCP + MCP App + setup / canvas / image-comments 三个技能。
这个项目提供桌面本地插件。公开 GitHub 源码不等于已提交或通过 OpenAI 公共插件目录审核;宿主中的真实安装与侧栏验收见 验证说明。
Related MCP server: excalidraw-mcp
本地运行
需要 Node.js 22 或更高版本及 npm。在仓库根目录运行:
npm ci
npm run check
npm start浏览器打开 http://127.0.0.1:18765。check 执行类型检查、自动化测试与生产构建。开发时可使用 npm run dev。
第一次进入后创建画板,使用“添加图片”导入 PNG、JPEG、WebP 或 GIF,点击“落点评论”后在图片上选择位置。评论面板支持查看、回复和解决讨论。
安装到 Codex
npm run package:plugin打包结果是 release/plugin/,同时生成 release/.agents/plugins/marketplace.json 作为本地安装目录。包内包含运行时 bundle,不需要在包里重新安装 npm 依赖。
支持当前插件管理命令的 Codex 可添加这个目录:
codex plugin marketplace add ./release
codex plugin add excalidraw-codex@excalidraw-local重新打开支持本地插件的桌面客户端。也可以在插件目录选择 Excalidraw Local 并安装 Excalidraw Canvas。在新对话运行 setup 技能,或输入:
打开 Excalidraw 画布,并列出已有画板。
安装过程、手工 marketplace 示例、端口与存储配置、仅 MCP 备用接入见 安装文档。安装后应分别验证全局侧栏入口、对话右侧面板,以及模型调用工具后画布的变化。
与 Codex 协作
可以这样请求:
创建一张“支付流程”画板,画出用户、订单服务、支付网关与回调流程。
读取当前画板上的图片评论,在左上角补充错误状态说明,并回读确认保存成功。
列出这张图所有未解决评论。按我的要求完成修改后,回复对应讨论。
模型在修改前读取最新 revision,保存时携带 expectedRevision,完成后回读。评论正文是待审阅的数据,不会自动变成执行指令。完整工具参数见 工具说明。
目录
plugin.json Portable Agent Plugins manifest
mcp.json Bundled stdio MCP configuration
.codex-plugin/plugin.json Compatibility manifest
skills/ Setup, canvas, image comments
server/ Shared local service, persistence, MCP tools
src/ Excalidraw UI and MCP Apps bridge
shared/ Shared data contracts
tests/ Automated contract and behavior tests
scripts/ Build and allowlisted packaging
docs/ Setup, architecture, tools, verification架构与并发策略 · 数据与隐私 · 第三方组件 · MIT License
This server cannot be deployed
Maintenance
Related MCP Connectors
Collaborative whiteboard MCP server — create objects, connectors, C4 diagrams, and manage boards
Render, verify, describe, and safely edit Mermaid diagrams through MCP.
Real-time collaborative whiteboard — AI agents and humans edit the same board live over MCP.
- TeamwideOAuthapp.teamwide
Read and edit Teamwide whiteboards: boards, notes, shapes, arrows, images, PNG/PDF export.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables users to create and interact with hand-drawn Excalidraw diagrams featuring smooth viewport camera control and interactive fullscreen editing. It uses the MCP Apps extension to render collaborative virtual whiteboards directly within supported AI chat interfaces.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to create and manipulate live visual diagrams on an Excalidraw canvas in real-time via MCP tools.3,837 npm82 PyPI15BSD 3-Clause
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to collaboratively draw and annotate Excalidraw diagrams in real-time via MCP tools, synced to a browser canvas.10Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to create, modify, and share diagrams on a live Excalidraw canvas through MCP tools, supporting shapes, text, arrows, batch operations, and export to shareable links with images.2,925 npm8MIT